© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27381
    Prev
    Next
    INDEX
    Explanations

    mentions of representation and diversity in media and commentary on culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    regar
    -0.07
    ALIGN
    -0.06
     Wikipedia
    -0.06
    alle
    -0.06
    edor
    -0.06
    uko
    -0.06
    .Throw
    -0.06
     altru
    -0.06
    kop
    -0.06
    ój
    -0.06
    POSITIVE LOGITS
     Maison
    0.07
    ä½Ļ
    0.06
    daily
    0.06
     readers
    0.06
    etz
    0.06
     Angiosper
    0.06
    atz
    0.06
    çek
    0.06
     deficit
    0.06
    antu
    0.06
    Activations Density 0.003%

    No Known Activations